Software Defect Prediction Using Machine Learning
P. L. S. Tejaswini1, K. Sree Varsha2, P. Yasaswini3, Sangeetha Yalamanchili4
1P. L. S. Tejaswini, IV/IV B.Tech Student, Department of IT, V.R Siddhartha Engineering College, Vijayawada (Andhra Pradesh), India.
2K. Sree Varsha, IV/IV B.Tech Student, Department of IT, V.R Siddhartha Engineering College, Vijayawada (Andhra Pradesh), India.
3P. Yasaswini, IV/IV B.Tech Student, Department of IT, V.R Siddhartha Engineering College, Vijayawada (Andhra Pradesh), India.
4Dr. Sangeetha Yalamanchili, Associate Professor, Department of IT, V.R Siddhartha Engineering College, Vijayawada (Andhra Pradesh), India.
Manuscript received on 13 October 2019 | Revised Manuscript received on 22 October 2019 | Manuscript Published on 02 November 2019 | PP: 1053-1057 | Volume-8 Issue-2S11 September 2019 | Retrieval Number: B11780982S1119/2019©BEIESP | DOI: 10.35940/ijrte.B1178.0982S1119
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Software defect prediction analysis is an important problem in the software engineering community. Software defect prediction can directly affect the quality and has achieved significant popularity in the last few years. This software prediction analysis helps in delivering the best development and makes the maintenance of software more reliable. This is because predicting the software faults in the earlier phase improves the software quality,efficiency, reliability and the overall cost in SDLC. Developing and improving the software defect prediction model is a challenging task and many techniques are introducing for better performance. Supervised ML algorithms have been used to predict future software faults based on historical data[1]. These classifiers are Naïve Bayes (NB), Support Vector Machine(SVM) and Artificial neural network(ANN). The evaluation process showed that ML algorithms can be used effectively with a high accuracy rate. The comparison is made with other machine learning algorithms to finds the algorithms which gives more accuracy. And the results show that machine learning algorithms gives the best performance. The existence of software defects affects dramatically on software reliability, quality, and maintenance cost. Achieving reliable software also is hard work, even the software applied carefully because most time there is hidden errors. In addition, developing a software defect prediction model which could predict the faulty modules in the early phase is a real challenge in software engineering. Software defect prediction analysis is an essential activity in software development. This is because predicting the bugs prior to software deployment achieves user satisfaction, and helps in increasing the overall performance of the software. Moreover, predicting software defects early improves software adaptation to different environments and increases resource utilization.
Keywords: Naïve Bayes, Support Vector Machine(SVM), Artificial Network Network(ANN), Software Defect Analysis, Reliability, Anaconda Navigator.
Scope of the Article: Machine Learning